context safety score
A score of 49/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 3 secret pattern match(es) in repository files
typosquat
Owner 'anthropics' impersonates Anthropic (the AI company). Anthropic's real GitHub presence is 'anthropic' or 'anthropic-ai', not 'anthropics'. Combined with repo name 'claude-plugins-official' this is designed to appear as an official Anthropic skill. Empty SKILL.md and no registry listing despite claimed 7.69M installs further indicate illegitimacy. (location: metadata.json (owner/full_name fields))
description injection
skill_description contains 'width=device-width, initial-scale=1' — an HTML meta viewport fragment, not a legitimate skill description. This suggests either metadata was scraped from a deceptive HTML page designed to poison the description field, or the field was intentionally filled with non-description content that could confuse downstream systems consuming this metadata. (location: metadata.json (skill_description field))
curl https://api.brin.sh/skill/anthropics%2Fclaude-plugins-official%2Fclaude-md-improverCommon questions teams ask before deciding whether to use this skill in agent workflows.
anthropics/claude-plugins-official/claude-md-improver currently scores 49/100 with a suspicious verdict and medium confidence. The goal is to protect agents from high-risk context before they act on it. Treat this as a decision signal: higher scores suggest lower observed risk, while lower scores mean you should add review or block this skill.
Use the score as a policy threshold: 80–100 is safe, 50–79 is caution, 20–49 is suspicious, and 0–19 is dangerous. Teams often auto-allow safe, require human review for caution/suspicious, and block dangerous.
brin evaluates four dimensions: identity (source trust), behavior (runtime patterns), content (malicious instructions), and graph (relationship risk). Analysis runs in tiers: static signals, deterministic pattern checks, then AI semantic analysis when needed.
Identity checks source trust, behavior checks unusual runtime patterns, content checks for malicious instructions, and graph checks risky relationships to other entities. Looking at sub-scores helps you understand why an entity passed or failed.
brin performs risk assessments on external context before it reaches an AI agent. It scores that context for threats like prompt injection, hijacking, credential harvesting, and supply chain attacks, so teams can decide whether to block, review, or proceed safely.
No. A safe verdict means no significant risk signals were detected in this scan. It is not a formal guarantee; assessments are automated and point-in-time, so combine scores with your own controls and periodic re-checks.
Re-check before high-impact actions such as installs, upgrades, connecting MCP servers, executing remote code, or granting secrets. Use the API in CI or runtime gates so decisions are based on the latest scan.
Learn more in threat detection docs, how scoring works, and the API overview.
Assessments are automated and may contain errors. Findings are risk indicators, not confirmed threats. This is a point-in-time assessment; security posture can change.
integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.